2017
DOI: 10.17678/beuscitech.344953
|View full text |Cite
|
Sign up to set email alerts
|

A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals

Abstract: A B S T R A C TElectrocardiography (ECG) is a useful test used commonly to observe the electrical activity of a heart.Recently, a growing relationship has been observed between diagnosis of any heart disease and using of machine learning techniques. In this scope, a diagnostic application model designed based on a

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0
4

Year Published

2019
2019
2022
2022

Publication Types

Select...
9
1

Relationship

3
7

Authors

Journals

citations
Cited by 30 publications
(10 citation statements)
references
References 23 publications
0
6
0
4
Order By: Relevance
“…Bu Eğrinin altındaki alan (EAA) modellerin performanslarını değerlendirmek için hesaplanmaktadır. Bu EAA değeri mükemmel bir sınıflandırmayı temsil ettiğinden, EAA için 1'e ulaşmak amaçlanmaktadır [26,28].…”
Section: Doğ = (Gp + Gn) (Gp + Yp + Gn + Yn)unclassified
“…Bu Eğrinin altındaki alan (EAA) modellerin performanslarını değerlendirmek için hesaplanmaktadır. Bu EAA değeri mükemmel bir sınıflandırmayı temsil ettiğinden, EAA için 1'e ulaşmak amaçlanmaktadır [26,28].…”
Section: Doğ = (Gp + Gn) (Gp + Yp + Gn + Yn)unclassified
“…Noise and interference can be undesirable which is it causes oscillations in signal processing applications. ECG involves an excessive number of unrestful noises, so this step has an important task for ECG classification application [35], [36]. Furthermore, it is applied as a usual analysis stage in most biomedical practice to obtain stable and clear signals.…”
Section: Preprocessingmentioning
confidence: 99%
“…Sharma et al [18] design a dual-band optimal bi-orthogonal wavelet filter to preprocess the ECG signal, and then use the k-nearest neighbor (KNN) method to implement classification of MI only using single lead. Diker et al [19] use recursive feature elimination (RFE) to select eleven features from morphological and statistical domains and use KNN and artificial neural network (ANN) methods to detect MI. Lui and Chow [20] use the data of the standard I lead on the PTB database to detect the MI using a convolutional recurrent neural network.…”
Section: Related Workmentioning
confidence: 99%